© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8313
    Prev
    Next
    INDEX
    Explanations

    first person verb phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    I write or I wanted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ƌ
    0.41
    いつでも
    0.40
    を目指
    0.39
    働く
    0.39
     ভবিষ্যতে
    0.38
    別途
    0.38
    渀
    0.38
    喩
    0.38
    尒
    0.37
    غط
    0.37
    POSITIVE LOGITS
     hereby
    0.70
     proudly
    0.54
     arrived
    0.48
     recently
    0.48
     respectfully
    0.48
     hesitated
    0.47
     gostaria
    0.47
    recently
    0.46
     excitedly
    0.46
     hesit
    0.46
    Activations Density 0.256%

    No Known Activations